A Cross-lingual Comparison of Human and Model Relative Word Importance
Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
Standard
A Cross-lingual Comparison of Human and Model Relative Word Importance. / Morger, Felix; Brandl, Stephanie; Beinborn, Lisa; Hollenstein, Nora.
Proceedings of the 2022 CLASP Conference on (Dis)embodiment. Association for Computational Linguistics (ACL), 2022. p. 11-23.Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - GEN
T1 - A Cross-lingual Comparison of Human and Model Relative Word Importance
AU - Morger, Felix
AU - Brandl, Stephanie
AU - Beinborn, Lisa
AU - Hollenstein, Nora
PY - 2022
Y1 - 2022
N2 - Relative word importance is a key metric for natural language processing. In this work, we compare human and model relative word importance to investigate if pretrained neural language models focus on the same words as humans cross-lingually. We perform an extensive study using several importance metrics (gradient-based saliency and attention-based) in monolingual and multilingual models, including eye-tracking corpora from four languages (German, Dutch, English, and Russian). We find that gradient-based saliency, first-layer attention, and attention flow correlate strongly with human eye-tracking data across all four languages. We further analyze the role of word length and word frequency in determining relative importance and find that it strongly correlates with length and frequency, however, the mechanisms behind these non-linear relations remain elusive. We obtain a cross-lingual approximation of the similarity between human and computational language processing and insights into the usability of several importance metrics.
AB - Relative word importance is a key metric for natural language processing. In this work, we compare human and model relative word importance to investigate if pretrained neural language models focus on the same words as humans cross-lingually. We perform an extensive study using several importance metrics (gradient-based saliency and attention-based) in monolingual and multilingual models, including eye-tracking corpora from four languages (German, Dutch, English, and Russian). We find that gradient-based saliency, first-layer attention, and attention flow correlate strongly with human eye-tracking data across all four languages. We further analyze the role of word length and word frequency in determining relative importance and find that it strongly correlates with length and frequency, however, the mechanisms behind these non-linear relations remain elusive. We obtain a cross-lingual approximation of the similarity between human and computational language processing and insights into the usability of several importance metrics.
M3 - Article in proceedings
SP - 11
EP - 23
BT - Proceedings of the 2022 CLASP Conference on (Dis)embodiment
PB - Association for Computational Linguistics (ACL)
T2 - 2022 CLASP Conference on (Dis)embodiment
Y2 - 15 September 2022 through 16 September 2022
ER -
ID: 331507496